Fluid-attenuated inversion recovery hyperintensity in acute ischemic stroke may not predict hemorrhagic transformation

Abstract

Background: Fluid-attenuated inversion recovery (FLAIR) hyperintensity within an acute cerebral infarct may reflect delayed onset time and increased risk of hemorrhage after thrombolysis. Given the important implications for clinical practice, we examined the prevalence of FLAIR hyperintensity in patients 3-6 h from stroke onset and its relationship to parenchymal hematoma (PH).

Methods: Baseline DWI and FLAIR imaging with subsequent hemorrhage detection (ECASS criteria) were prospectively obtained in patients 3-6 h after stroke onset from the pooled EPITHET and DEFUSE trials. FLAIR hyperintensity within the region of the acute DWI lesion was rated qualitatively (dichotomized as visually obvious or subtle (i.e. only visible after careful windowing)) and quantitatively (using relative signal intensity (RSI)). The association of FLAIR hyperintensity with hemorrhage was then tested alongside established predictors (very low cerebral blood volume (VLCBV) and diffusion (DWI) lesion volume) in logistic regression analysis.

Results: There were 49 patients with pre-treatment FLAIR imaging (38 received tissue plasminogen activator (tPA), 5 developed PH). FLAIR hyperintensity within the region of acute DWI lesion occurred in 48/49 (98%) patients, was obvious in 18/49 (37%) and subtle in 30/49 (61%). Inter-rater agreement was 92% (κ = 0.82). The prevalence of obvious FLAIR hyperintensity did not differ between studies obtained in the 3-4.5 h and 4.5-6 h time periods (40% vs. 33%, p = 0.77). PH was poorly predicted by obvious FLAIR hyperintensity (sensitivity 40%, specificity 64%, positive predictive value 11%). In univariate logistic regression, VLCBV (p = 0.02) and DWI lesion volume (p = 0.03) predicted PH but FLAIR lesion volume (p = 0.87) and RSI (p = 0.11) did not. In ordinal logistic regression for hemorrhage grade adjusted for age and baseline stroke severity (NIHSS), increased VLCBV (p = 0.002) and DWI lesion volume (p = 0.003) were associated with hemorrhage but FLAIR lesion volume (p = 0.66) and RSI (p = 0.35) were not.

Conclusions: Visible FLAIR hyperintensity is almost universal 3-6 h after stroke onset and did not predict subsequent hemorrhage in this dataset. Our findings question the value of excluding patients with FLAIR hyperintensity from reperfusion therapies. Larger studies are required to clarify what implications FLAIR-positive lesions have for patient selection.

Fig. 1

Examples of DWI and FLAIR hyperintensity. A ‘Subtle’ FLAIR abnormality not identifiable with standard windowing of FLAIR (middle panel) but apparent after careful windowing and, in this case, application of a color scale (right-hand panel). B ‘Obvious’ FLAIR hyperintensity visible with standard windowing (middle panel). The right-hand panel shows lesion (red in online version) and mirror (green in online version) FLAIR hyperintensity ROIs used to calculate RSI.